© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38527
    Prev
    Next
    INDEX
    Explanations

    laboratory research collaborators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èīºèĢĥ
    -0.08
    æľįåĬ¡äººåijĺ
    -0.08
    perator
    -0.08
     EDUCA
    -0.08
    chau
    -0.08
    æ¥ŃèĢħ
    -0.08
    cius
    -0.08
    æķĻèĤ²å·¥ä½ľèĢħ
    -0.08
    ä»»ä½ķä¸Ģç§į
    -0.08
    skr
    -0.08
    POSITIVE LOGITS
     research
    0.15
    research
    0.12
     Research
    0.12
     collaborating
    0.12
    çļĦçłĶ究
    0.11
    Research
    0.11
     collaborators
    0.11
     collaboration
    0.11
     experiments
    0.10
    çłĶ究æĸ¹åIJij
    0.10
    Activations Density 0.556%

    No Known Activations